SQ

sqlcoder

SqlcoderGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters15.8B
Context8K
Layers40
Architecturestarcoder
Smallest quant6.7 GB
Quick answer

sqlcoder needs about 10.6 GB of memory at Q4_K_M (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 6.7 GB (Q2_K) to 16.8 GB (Q8_0).

15B parameter model for converting natural language to SQL queries

sqlcoder is a 15.8B parameter model fine‑tuned on StarCoder for natural language to SQL generation. It supports 8192 token context and is available in multiple GGUF quantisations. The model is licensed under CC BY‑SA 4.0 with OpenRAIL‑M clauses.

Good at

  • SQL generation from natural language
  • Handles complex queries
  • Fine‑tuned on diverse schemas

Limits

  • No vision support
  • Requires 8k context for full capability
  • License requires open‑source modifications if weights are altered

Best for

  • Building SQL query assistants
  • Automating database queries
  • Educational tools for SQL learning

Who it’s for. Developers and data analysts needing a local LLM to translate natural language into SQL. It is suitable for projects that require a licensed, open‑source solution with fine‑tuned performance on SQL tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.7 GB 7.4 GB
Tight Get file →
Q3_K_S6.9 GB 7.6 GB
Tight Get file →
Q3_K_M8.2 GB 8.8 GB
Too big Get file →
Q4_09.0 GB 9.7 GB
Too big Get file →
Q4_K_S9.1 GB 9.7 GB
Too big Get file →
Q3_K_L9.1 GB 9.8 GB
Too big Get file →
Q4_K_M10.0 GB 10.6 GB
Too big Get file →
Q5_010.9 GB 11.6 GB
Too big Get file →
Q5_K_S10.9 GB 11.6 GB
Too big Get file →
Q5_K_M11.5 GB 12.2 GB
Too big Get file →
Q6_K13.0 GB 13.7 GB
Too big Get file →
Q8_016.8 GB 17.5 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (6.73 GB) or Q3_K_S (6.93 GB). For 12‑GB VRAM, Q4_K_M (9.96 GB) or Q5_K_M (11.54 GB) are suitable. Larger GPUs can run higher‑quality quants like Q6_K (12.99 GB) or Q8_0 (16.82 GB). Memory estimates are approximate.

What GPU do you need for sqlcoder?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q3_K_S (6.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_0 (10.9 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.0 GB file, about 13.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.8 GB file, about 17.5 GB in use).

Which sqlcoder quant should you choose?

Q4_K_M is the usual starting point for sqlcoder: it balances file size and quality well. Here it is a 10.0 GB file.

The Q8_0 file is 16.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 6.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder
Parameters15.8B
Layers40
Trained context8,192 tokens
KV cache (fp16)20 KB per token

Source

Quantized byTheBloke
FamilySqlcoder
Base modeldefog/sqlcoder
Licenseother
Downloads (HF)2,153
Last updated2023-09-27

Frequently asked questions about sqlcoder

How much VRAM does sqlcoder need?

About 10.6 GB at Q4_K_M with an 8K context window. That is the 10.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run sqlcoder on an 8 GB GPU?

Yes, with Q3_K_S: the 6.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sqlcoder GGUF?

It depends on the quant: Q2_K is 6.7 GB, Q3_K_S is 6.9 GB, Q3_K_M is 8.2 GB, Q4_0 is 9.0 GB, Q4_K_S is 9.1 GB, Q3_K_L is 9.1 GB and 6 more.

What context length does sqlcoder support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download sqlcoder GGUF?

The files are on Hugging Face in the TheBloke/sqlcoder-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does sqlcoder use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Does sqlcoder support vision tasks?

No, the model has no vision capabilities and is focused solely on text and SQL generation.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Sqlcoder models

All Sqlcoder →

Other medium models

All medium models →